Algorithm for Semi-Supervised Learning in Image Retrieval

In this paper, based on Support Vector Machine (SVM), we introduce a semi-supervised learning algorithm for image retrieval. The basic consideration of the algorithm is that, if two data points are close to each other, they should share the same label. Therefore, it is reasonable to search a projection with maximal margin and locality preserving property. Comparing our algorithm to standard SVM and transductive SVM, Experimental results show efficiency and effectiveness of our algorithm.